TensorFlow 不仅仅是用来机器学习,它更可以用来模拟仿真。在这里,我们将通过模拟仿真几滴落入一块方形水池的雨点的例子,来引导您如何使用 TensorFlow 中的偏微分方程来模拟仿真的基本使用方法。
参考[url]http://wiki.jikexueyuan.com/project/tensorflow-zh/tutorials/pdes.html[/url]
[url]https://stackoverflow.com/questions/28237210/image-does-not-display-in-ipython/42567537?utm_medium=organic&utm_source=google_rich_qa&utm_campaign=google_rich_qa[/url]
代码运行不了
修改如下
把display(Image(data=f.getvalue()))
改成
scipy.misc.imsave("testimg.jpg", a)
image = PIL.Image.open("testimg.jpg")
image.show()
python hello.py
[img]http://dl2.iteye.com/upload/attachment/0130/0049/ecfe97d0-e884-32f2-af79-ffc3e7cd1cce.png[/img]
完整版还不完美的图片闪现的版本
参考[url]http://wiki.jikexueyuan.com/project/tensorflow-zh/tutorials/pdes.html[/url]
[url]https://stackoverflow.com/questions/28237210/image-does-not-display-in-ipython/42567537?utm_medium=organic&utm_source=google_rich_qa&utm_campaign=google_rich_qa[/url]
代码运行不了
修改如下
yum install libpng-devel freetype-devel -y
yum install tcl tk tix-devel -y
yum install tk-devel tcl-devel -y
yum -y install tkinter
virtualenv pianweifen
pip install --upgrade pip
#pip-10.0.1
pip install tensorflow
pip install matplotlib
pip install pillow
pip install ipython
pip install scipy
把display(Image(data=f.getvalue()))
改成
scipy.misc.imsave("testimg.jpg", a)
image = PIL.Image.open("testimg.jpg")
image.show()
# encoding: utf-8
#导入模拟仿真需要的库
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#导入可视化需要的库
import PIL.Image
from cStringIO import StringIO
#from io import BytesIO
import scipy.misc
from IPython.display import clear_output, Image, display
def DisplayArray(a, fmt='jpeg', rng=[0,1]):
"""Display an array as a picture."""
a = (a - rng[0])/float(rng[1] - rng[0])*255
a = np.uint8(np.clip(a, 0, 255))
f = StringIO()
# f = BytesIO()
PIL.Image.fromarray(a).save(f, fmt)
# display(Image(data=f.getvalue()))
scipy.misc.imsave("testimg.jpg", a)
image = PIL.Image.open("testimg.jpg")
image.show()
#def DisplayArray(a, rng=[0 ,1]):
# plt.ion()
# a = (a - rng[0])/float(rng[1]-rng[0])*255
# a = np.uint8(np.clip(a, 0, 255))
# print(a)
# plt.imshow(a, cmap='gray')
# plt.pause(1)
# plt.close()
sess = tf.InteractiveSession()
def make_kernel(a):
"""Transform a 2D array into a convolution kernel"""
a = np.asarray(a)
a = a.reshape(list(a.shape) + [1,1])
return tf.constant(a, dtype=1)
def simple_conv(x, k):
"""A simplified 2D convolution operation"""
x = tf.expand_dims(tf.expand_dims(x, 0), -1)
y = tf.nn.depthwise_conv2d(x, k, [1, 1, 1, 1], padding='SAME')
return y[0, :, :, 0]
def laplace(x):
"""Compute the 2D laplacian of an array"""
laplace_k = make_kernel([[0.5, 1.0, 0.5],
[1.0, -6., 1.0],
[0.5, 1.0, 0.5]])
return simple_conv(x, laplace_k)
N = 500
# Initial Conditions -- some rain drops hit a pond
# Set everything to zero
u_init = np.zeros([N, N], dtype="float32")
ut_init = np.zeros([N, N], dtype="float32")
# Some rain drops hit a pond at random points
for n in range(40):
a,b = np.random.randint(0, N, 2)
u_init[a,b] = np.random.uniform()
DisplayArray(u_init, rng=[-0.1, 0.1])
]
python hello.py
[img]http://dl2.iteye.com/upload/attachment/0130/0049/ecfe97d0-e884-32f2-af79-ffc3e7cd1cce.png[/img]
完整版还不完美的图片闪现的版本
# encoding: utf-8
#导入模拟仿真需要的库
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#导入可视化需要的库
import PIL.Image
from cStringIO import StringIO
#from io import BytesIO
import scipy.misc
from IPython.display import clear_output, Image, display
def DisplayArray(a, fmt='jpeg', rng=[0,1]):
"""Display an array as a picture."""
a = (a - rng[0])/float(rng[1] - rng[0])*255
a = np.uint8(np.clip(a, 0, 255))
f = StringIO()
# f = BytesIO()
PIL.Image.fromarray(a).save(f, fmt)
#display(Image(data=f.getvalue()))
scipy.misc.imsave("testimg.jpg", a)
image = PIL.Image.open("testimg.jpg")
image.show()
sess = tf.InteractiveSession()
def make_kernel(a):
"""Transform a 2D array into a convolution kernel"""
a = np.asarray(a)
a = a.reshape(list(a.shape) + [1,1])
return tf.constant(a, dtype=1)
def simple_conv(x, k):
"""A simplified 2D convolution operation"""
x = tf.expand_dims(tf.expand_dims(x, 0), -1)
y = tf.nn.depthwise_conv2d(x, k, [1, 1, 1, 1], padding='SAME')
return y[0, :, :, 0]
def laplace(x):
"""Compute the 2D laplacian of an array"""
laplace_k = make_kernel([[0.5, 1.0, 0.5],
[1.0, -6., 1.0],
[0.5, 1.0, 0.5]])
return simple_conv(x, laplace_k)
N = 500
# Initial Conditions -- some rain drops hit a pond
# Set everything to zero
u_init = np.zeros([N, N], dtype="float32")
ut_init = np.zeros([N, N], dtype="float32")
# Some rain drops hit a pond at random points
for n in range(40):
a,b = np.random.randint(0, N, 2)
u_init[a,b] = np.random.uniform()
DisplayArray(u_init, rng=[-0.1, 0.1])
eps = tf.placeholder(tf.float32, shape=())
damping = tf.placeholder(tf.float32, shape=())
# Create variables for simulation state
U = tf.Variable(u_init)
Ut = tf.Variable(ut_init)
# Discretized PDE update rules
U_ = U + eps * Ut
Ut_ = Ut + eps * (laplace(U) - damping * Ut)
# Operation to update the state
step = tf.group(
U.assign(U_),
Ut.assign(Ut_))
# Initialize state to initial conditions
tf.initialize_all_variables().run()
# Run 1000 steps of PDE
for i in range(1000):
# Step simulation
step.run({eps: 0.03, damping: 0.04})
# Visualize every 50 steps
if i % 50 == 0:
clear_output()
DisplayArray(U.eval(), rng=[-0.1, 0.1])